Counterfactual Neighborhood Risk Fields: Evidence-Grounded Selective Safety for Vision-Language Models
arXiv:2610.20679v1 Announce Type: new Abstract: Representation-based safety defenses for vision-language models (VLMs) often learn to separate harmful from benign inputs, but separation alone does not establish what a risk score means or when it should be trusted. We introduce Counterfactual Neighb…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-10-16 04:00 · arXiv cs.AI
Counterfactual Neighborhood Risk Fields: Evidence-Grounded Selective Safety for Vision-Language Models